Related papers: Assessment of Response Time for New Multi Level Fe…
Large language models (LLMs) have revolutionized applications such as code completion, chatbots, and online classification. To elevate user experiences, service level objectives (SLOs) serve as crucial benchmarks for assessing inference…
Efficiently serving Large Language Models (LLMs) requires selecting an optimal parallel execution plan, balancing computation, memory, and communication overhead. However, determining the best strategy is challenging due to varying…
Large language models (LLMs) often benefit from verbalized reasoning at inference time, but it remains unclear which aspects of task difficulty these extra reasoning tokens address. To investigate this question, we formalize a framework…
This paper formulates the Embodied Questions Answering (EQsA) problem, introduces a corresponding benchmark, and proposes an agentic system to tackle the problem. Classical Embodied Question Answering (EQA) is typically formulated as…
Synaptic delay parameterization of neural network models have remained largely unexplored but recent literature has been showing promising results, suggesting the delay parameterized models are simpler, smaller, sparser, and thus more…
Most commercial embedded devices have been deployed with a single processor architecture. The code size and complexity of applications running on embedded devices are rapidly increasing due to the emergence of application business models…
Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable…
Dynamic voltage scaling (DVS) is one of the most effective techniques for reducing energy consumption in embedded and real-time systems. However, traditional DVS algorithms have inherent limitations on their capability in energy saving…
In modern computer systems, jobs are divided into short tasks and executed in parallel. Empirical observations in practical systems suggest that the task service times are highly random and the job service time is bottlenecked by the…
Modular quantum computing provides a scalable approach to overcome the limitations of monolithic quantum architectures by interconnecting multiple Quantum Processing Units (QPUs) through a quantum network. In this work, we explore and…
Facts change over time, making it essential for Large Language Models (LLMs) to handle time-sensitive factual knowledge accurately and reliably. Although factual Time-Sensitive Question-Answering (TSQA) tasks have been widely developed,…
LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…
In recent years, the development of specialized edge computing devices has significantly increased, driven by the growing demand for AI models. These devices, such as the NVIDIA Jetson series, must efficiently handle increased data…
We study a mutually enriching connection between response time analysis in real-time systems and the mixing set problem. Thereby generalizing over known results we present a new approach to the computation of response times in…
We study the scheduling of flows on a switch with the goal of optimizing metrics related to the response time of the flows. The input to the problem is a sequence of flow requests on a switch, where the switch is represented by a bipartite…
Modern computing paradigms, such as cloud computing, are increasingly adopting GPUs to boost their computing capabilities primarily due to the heterogeneous nature of AI/ML/deep learning workloads. However, the energy consumption of GPUs is…
We study sequential interval scheduling when task start and end times are random. The set of tasks and their weights are known in advance, while each task's start and end times are drawn from known discrete distributions and revealed only…
Large-batch training has been essential in leveraging large-scale datasets and models in deep learning. While it is computationally beneficial to use large batch sizes, it often requires a specially designed learning rate (LR) schedule to…
Scheduling with testing is a recent online problem within the framework of explorable uncertainty motivated by environments where some preliminary action can influence the duration of a task. Jobs have an unknown processing time that can be…
A novel energy reduction strategy to maximally exploit the dynamic workload variation is proposed for the offline voltage scheduling of preemptive systems. The idea is to construct a fully-preemptive schedule that leads to minimum energy…